19 citations · 147 across the 38 of their papers we have counts for
Showing 2026 · cs.CLShow all
2 papers · 2 filters
cs.CL2026
Language-model ratings of depression reflect the rater more than the patient
Baihan Lin
Depression has no diagnostic blood test. Language models promise tireless, consistent assessment, but can accurate raters disagree about individuals? We pre-registered 880 language…
cs.CL2026
Distilling Bayesian Belief States into Language Models for Auditable Negotiation
Zongqi Cui, Baihan Lin
Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs)…